Autonomous Vehicle Path Planning Using Motion Primitives
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in safely operating in dynamic environments due to rapid changes and insufficient sensor data, leading to uncertainty in safe movements and potential safety risks.
Innovation Solution
A computer-implemented method and system that processes sensor data to assess risks and determines motion primitives for safe stopping, including a first and second movement, to ensure the vehicle can safely stop even in fault conditions where sensor data is limited or unavailable.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If the autonomous vehicle relies on sensor data for navigation and safety decisions, then the vehicle can operate autonomously in dynamic environments, but sensor failures or insufficient data lead to uncertainty and safety risks
Solution Approach 1:
The system pre-computes multiple path plans (normal path plan and safe path plan) in advance before fault conditions occur. The safe path plan is specifically prepared for fault scenarios, allowing the vehicle to quickly switch to a pre-planned safe trajectory without real-time computation delays when sensors fail.
Solution Approach 2:
The system prepares contingency measures in advance by generating a safe path plan that acts as a cushion against potential sensor failures. This pre-prepared fallback plan ensures that even if primary sensors fail, the vehicle has a pre-computed safe trajectory to follow, cushioning the impact of the failure on safety.
2Adaptability or versatility
If the vehicle continuously processes sensor data and updates path plans, then the vehicle can adapt to rapid environmental changes, but computational complexity and processing time increase
Solution Approach 1:
The path planning is segmented into distinct components: a normal path plan for routine navigation and a safe path plan for fault conditions. This segmentation allows the system to process different types of path information separately, reducing the complexity of handling all possible scenarios in a single monolithic planning system.
Solution Approach 2:
The system computes a safe path plan that extends beyond the immediate needs, potentially covering longer time horizons and more conservative safety margins than strictly necessary. This excessive action ensures that the pre-computed safe path remains valid even under uncertain or rapidly changing conditions, reducing the need for frequent re-computation.
3Productivity
If the vehicle executes a single path plan to reach the destination, then the navigation is simple and direct, but the vehicle cannot ensure safety when fault conditions occur during operation
Solution Approach 1:
The safe path plan is computed in advance alongside the normal path plan, before any fault conditions occur. This preliminary computation of the safe path ensures that when sensors fail, the vehicle can immediately switch to a pre-computed safe trajectory without delaying navigation or requiring complex real-time decision-making.
Solution Approach 2:
The safe path plan acts as an intermediary solution between the normal operation mode and fault condition response. Instead of directly switching from normal navigation to emergency stopping, the system uses the pre-computed safe path plan as an intermediate trajectory that guides the vehicle to a safe location, maintaining navigation efficiency while ensuring safety.
Data Source
AI summary
Various software techniques for managing operation of autonomous vehicles based on sensor data are disclosed herein. A computing system may generate, based on a set of signals descriptive of a current state of an environment in which the autonomous vehicle is operating, a normal path plan separate from a safe path plan, or a hybrid path plan including a normal path plan and a safe path plan. In generating the safe path plan, the computing system may generate and concatenate a set of motion primitives. When a fault condition occurs, the computing device may transition from executing the normal path plan to executing the safe path plan to safely stop the autonomous vehicle.